© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42648
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    迹象
    -0.28
    >m
    -0.25
    Too
    -0.25
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.25
     seventy
    -0.25
    约
    -0.24
    éĢģç»Ļ
    -0.24
     packs
    -0.24
     privilege
    -0.24
    ecn
    -0.23
    POSITIVE LOGITS
    è¿ij
    0.54
     well
    0.38
     over
    0.31
     Near
    0.31
     close
    0.31
     WELL
    0.30
     almost
    0.30
     Close
    0.30
     near
    0.28
     Well
    0.28
    Activations Density 0.002%

    No Known Activations